We present an image processing pipeline for highly accurate registration of postoperative CT to preoperative MR in the context of Deep Brain Stimulation (DBS) planning. Our method consists of a fully automatic pre-alignment using fuzzy connectedness and an intensity-based rigid registration based on the Normalized Gradient Fields distance measure. The accuracy of our method was extensively evaluated on 20 DBS datasets from clinical routine and compared with three manual expert registrations each. The average registration error was 0.95 mm in the target region as compared to an inter-observer variability of 1.12 mm. The average computation time was about five seconds.