To improve vehicle utilization and maximize resource efficiency in road freight transportation, this paper proposes a vehicle-cargo matching method based on view similarity, following case-based reasoning (CBR) principles. First, vehicle and cargo information is formally represented using a knowledge description system, enabling initial classification and matching through vehicle CR attributes and cargo N attributes. Subsequently, K-means clustering is performed on the vehicle dataset, and Mahalanobis distance is used to determine the cluster most similar to the cargo to be matched, thereby reducing the search space. An enhanced view-similarity calculation method is then introduced, where Euclidean distance is used to measure similarity between the target cargo and vehicles within the selected cluster. Experimental results show that the proposed method yields higher discrimination in matching results, with a maximum similarity of 0.848. Moreover, vehicle loading rates are significantly improved, with matching efficiency increased by about 76%. This method offers an effective approach for optimizing vehicle-cargo allocation in full-truck-load scenarios.