Cone-beam X-ray computed tomography (CT) is attracting increasing attention due to its applications in medicine, biomedical sciences, material engineering, and non-destructive industrial evaluation. Rapid volumetric image reconstruction is highly desirable in all these fields for prompt visualization and analysis of complex structures of interest. However, in most applications, volumetric image reconstruction is still a very demanding computational task. The Cell Broadband Engine architecture (CBEA) is a novel microprocessor architecture designed to provide power-efficient and cost-effective highperformance processing for some of the world's most demanding applications, including next generation game consoles. Applications that show special promise of benefiting from CBEA are medical imaging, security and surveillance, digital media, entertainment, communications, and certain scientific workloads. We believe that the CBEA is a good vehicle for processing 3D CT image reconstructions because it has the capability of reaching 200 Gfps. We implemented 3D CT image reconstruction on the CBEA. However, the programming scheme of the CBEA is different from single-core architectures. To archive peak performance on the CBEA, coding optimizations are needed to exploit the unique features of the hardware. In this paper, we describe the parallelization of the 3D image reconstruction algorithm on the CBEA. The results show that the CBEA can achieve significant run time savings. Copyright © 2009 John Wiley & Sons, Ltd.