High-density LSI packages such as ball grid array (BGA) are being utilised in the car electronics and communications infrastructure products. These products require a high-speed and reliable inspection technique for their solder joints. In this paper, we propose an automated X-ray inspection technique for BGA mounted substrate based on oblique computed tomography (OCT). Automated inspection consists of OCT capturing, position adjustment, bump extraction, character extraction and judgment. We proposed five characteristic features related to the bump shape. Moreover, by combining the characteristic features using artificial neural network, the condition of a solder bump was determined. In the experiments, we evaluate these techniques using actual BGA-mounted substrate. As a result, the correct rate of judgment reached 99.7%, which shows the clearly indicates that our method may be useful in the practice.