Multiple-input multiple-output (MIMO) radar waveforms design with specified properties has a number of superiority over its phased-array counterpart, such as clutter suppression and interference mitigation. In this paper, we consider the problem of waveform optimization with prior information on targets of interest to improve the parameter estimation performance of MIMO radar in the presence of signal-dependent noise, which is based on the constrained Cramer-Rao bound (CRB). The waveform covariance matrix (WCM) is designed to minimize the trace of the constrained CRB such that the parameter estimation performance can be improved. In order to solve the resultant nonlinear optimization problem, a novel diagonal loading (DL) based method is proposed to relax this optimization issue as a semidefinite programming (SDP) one, which can be solved very efficiently. Following that, an optimal solution to the initial issue can be obtained via the least squares (LS) fitting of the solution acquired by the relaxed one. The effectiveness of the proposed method is verified by numerical examples, as compared to the uncorrelated waveforms.