Tall trees that are ecologically important because of their large biomass and stored carbon may be declining due to warming associated with climate change. This study demonstrates Light Detection and Ranging (LiDAR) data collected in the Great Smoky Mountains National Park can be used to detect tallest trees in a complex mixed forest. It also highlights a methodology for processing large data volumes for quantifying and visualizing vegetation structure. Ten tall tree sites within the park were identified in the LiDAR dataset. And eight sites were field inspected to measure tree heights. A subset of the park also was examined to automatically extract tree objects from the LiDAR point cloud and compute structural parameters such as height, stem diameter, and canopy width. Multivariate regression modeling was performed to determine if LiDAR-derived datasets are efficient baselines for the modeling of environmental variables associated with tree growth.