Minimally invasive trans-catheter aortic valve implantation (TAVI) procedure can be greatly facilitated using smart visualization and guidance technology involving the 3-D model of the aorta. In this paper, a hybrid method is proposed for contrast-based registration between the 3-D model and angiography of the aorta during TAVI procedures. By integrating the information of aorta segmentation and aortic landmark detection into intensitybased registration, the proposed method combines the merits of intensity-based registration and feature/landmark-based registration. In addition, the challenging task of explicit feature/landmark extraction on 2-D images is avoided. Experiments on 9 real clinical data achieved an average registration error of 2.14±0.49 pixels, demonstrating the efficacy of the proposed method.