This study evaluated the machine-dependent three-dimensional geometric distortion images acquired from a 1.5T 700 mm-wide bore MR-simulator based on a large geometric accuracy phantom. With the consideration of radiation therapy (RT) application requirements, every sequence was examined in various combinations of acquisition-orientations and receiver-bandwidths with console-integrated distortion correction enabled. Distortion was repeatedly measured over a six-month period. The distortion measured from the images acquired at the beginning of this period was employed to retrospectively correct the distortion in the subsequent acquisitions. Geometric distortion was analyzed within the largest field-of-view allowed. Six sequences were examined for comprehensive distortion analysis—VIBE, SPACE, TSE, FLASH, BLADE and PETRA. Based on optimal acquisition parameters, their diameter-sphere-volumes (DSVs) of CT-comparable geometric fidelity (where 1 mm distortion was allowed) were 333.6 mm, 315.1 mm, 316.0 mm, 318.9 mm, 306.2 mm and 314.5 mm respectively. This was a significant increase from 254.0 mm, 245.5 mm, 228.9 mm, 256.6 mm, 230.8 mm and 254.2 mm DSVs respectively, when images were acquired using un-optimized parameters. The longitudinal stability of geometric distortion and the efficacy of retrospective correction of console-corrected images, based on prior distortion measurements, were inspected using VIBE and SPACE. The retrospectively corrected images achieved over 500 mm DSVs with 1 mm distortion allowed. The median distortion was below 1 mm after retrospective correction, proving that obtaining prior distortion map for subsequent retrospective distortion correction is beneficial. The systematic evaluation of distortion using various combinations of sequence-type, acquisition-orientation and receiver-bandwidth in a six-month time span would be a valuable guideline for optimizing sequence for various RT applications.