Resource discovery is a basic service in grid computing : gives a description of resources desired and finds the available one to match the description. In computational grid, how to discover resources efficiently has become a crucial factor to evaluate the performance in the whole system. In this paper, we present a bid-based resource discovery algorithm, which converts a resource request into a bidding letter and sends it to a group of physical services owned by the same virtual service to call for bidding. All resources receiving bidding letter make offers to bid according to our algorithm. Job manager selects the best one to response client request. To evaluate the performance of our method, we compare our system with the centralized and peer-to-peer resource discovery approaches. The analysis results show that our system reduces average response time of jobs, leverages the cost of the resource discovery, and improves the system scalability.