The similarity of a pair of images can be measured using the distance measurement method from the feature extraction. The feature extraction method used in this research was the Scale Invariant Feature Transform (SIFT). This method is an extraction method that is invariant to changes in scale, rotation, translation and illumination. In this research, each keypoint of test image is matched for its level of similarity with the Euclidean distance method. The similarity of each keypoint of the tested image is matched by Euclidean distance and it will be claimed similar if it has the smallest distance. Next, the corresponding keypoint of the tested image gets recall test by varying parameters of transformation in size, rotation, color, and angle as well as different image. The research results demonstrated that the recall averages of dataset were 100 for similar image test, 95 for size and rotation changes tests, 98 for colour changes test, 97 for angle changes test, and 0 for image test with different objects. Based on the results, SIFT is suitable for detecting the similarity of image object shapes.