Since bridge components are usually subject to similar environmental conditions, their deteriorations are usually correlated. Discovering meaningful patterns and association rules in bridge inspection data is useful to establish cost-effective maintenance policies. It is also of fundamental importance to utilize useful techniques to assist the bridge managers to diagnose potential bridge failure origins, which may lead to catastrophic consequences. Market basket analysis (MBA), also known as association rule mining, is an effective data mining method used to identify which items are most frequently occurred jointly. This paper employs MBA to discover deterioration patterns by extracting associations or co-occurrences from the inspection database of highway bridges. By induction of the association rule, sets of data instances that frequently appear together can be founded. The results demonstrate the capability of this approach, which can help the bridge managers to better identify the interdependencies of deteriorated bridge components and make a proper bridge maintenance strategy.